metadata
base_model: google/vit-base-patch16-224
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: SupViT Model (model_idx_0753)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 753 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9213 |
| Val Accuracy | 0.8477 |
| Test Accuracy | 0.8422 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, oak_tree, tiger, apple, beetle, sunflower, chimpanzee, pickup_truck, butterfly, rose, mouse, cup, lion, seal, mushroom, crocodile, sea, shark, house, table, bowl, leopard, wolf, bee, worm, rabbit, willow_tree, wardrobe, tank, trout, snail, fox, baby, clock, bicycle, train, aquarium_fish, skunk, bus, cattle, woman, lizard, poppy, elephant, palm_tree, turtle, bear, possum, skyscraper, bed